12-cs01-eda
2/21/23
Time Spent
Difficulty
Population over time
DONOHUE_DF |>
group_by(YEAR) |>
summarise(Population = sum(Population)) |>
ggplot(aes(x = YEAR, y = Population)) +
geom_line() +
scale_x_continuous(
breaks = seq(1980, 2010, by = 1),
limits = c(1980, 2010),
labels = c(seq(1980, 2010, by = 1))
) +
labs(
title = "Population has steadily increased",
x = "Year",
y = "Population"
) +
theme_minimal() +
theme(axis.text.x = element_text(angle = 90),
plot.title.position = "plot")
Crime over time
df |>
ggplot(aes(x = YEAR, y = Viol_crime_rate_100k_log)) +
geom_line() +
scale_x_continuous(
breaks = seq(1980, 2010, by = 1),
limits = c(1980, 2010),
labels = c(seq(1980, 2010, by = 1))
) +
scale_y_continuous(
breaks = seq(5.75, 6.75, by = 0.25),
limits = c(5.75, 6.75)
) +
labs(
title = "Crime rates fluctuate over time",
x = "Year",
y = "ln(violent crimes per 100,000 people)"
) +
theme_minimal() +
theme(axis.text.x = element_text(angle = 90),
plot.title.position = "plot")
Crime over time by state
p <- DONOHUE_DF |>
mutate(Viol_crime_rate_100k_log = log((Viol_crime_count * 100000) / Population)) |>
ggplot(aes(x = YEAR, y = Viol_crime_rate_100k_log, color = STATE)) +
geom_point(size = 0.5) +
geom_line(aes(group = STATE),
size = 0.5,
show.legend = FALSE
) +
geom_text_repel(data = DONOHUE_DF |>
mutate(Viol_crime_rate_100k_log = log((Viol_crime_count * 100000) / Population)) |>
filter(YEAR == last(YEAR)),
aes(label = STATE,x = YEAR, y = Viol_crime_rate_100k_log),
size = 3, alpha = 1, nudge_x = 1, direction = "y",
hjust = 1, vjust = 1, segment.size = 0.25, segment.alpha = 0.25,
force = 1, max.iter = 9999)p +
guides(color = "none") +
scale_x_continuous(
breaks = seq(1980, 2015, by = 1),
limits = c(1980, 2015),
labels = c(seq(1980, 2010, by = 1), rep("", 5))
) +
scale_y_continuous(
breaks = seq(3.5, 8.5, by = 0.5),
limits = c(3.5, 8.5)
) +
labs(
title = "States have different levels of crime",
x = "Year", y = "ln(violent crimes per 100,000 people)"
) +
theme_minimal() +
theme(axis.text.x = element_text(angle = 90), plot.title.position = "plot")
Police Presence over time
DONOHUE_DF |>
group_by(YEAR) |>
summarise(Police = sum(police_per_100k_lag)) |>
ggplot(aes(x = YEAR, y = Police)) +
geom_line() +
scale_x_continuous(
breaks = seq(1980, 2010, by = 1),
limits = c(1980, 2010),
labels = c(seq(1980, 2010, by = 1))
) +
labs(
title = "Police Presence has increased over time with fluctuations",
x = "Year",
y = "Police Presence per 100K people"
) +
theme_minimal() +
theme(axis.text.x = element_text(angle = 90),
plot.title.position = "plot")
Where to go from here?
- Implement some of these ideas
- This week’s lab - continues the EDA!
- Consider what variables we have that we haven’t looked at
- Consider the variables we have looked at but look at them differently
- Eventually: incorporate some of this and likely some of lab into your final case study
